BioTender-max/awesome-bio-agent-skills

ATAC Seq processes bulk ATAC-seq data with QC, MACS3 peak calling, consensus peak matrices, differential accessibility, and motif or footprint follow-up. Use it for paired-end ATAC analyses that need assay validation and downstream accessibility summaries.

AlphaFold validates protein designs with structure prediction for single chains and complexes. Use it to check folding, predict binder-target interfaces, and review confidence metrics like pLDDT, pTM, and ipTM.

BindCraft Binder Design generates protein binders with built-in AlphaFold2 validation and joint backbone/sequence optimization. Use it for production binder campaigns and protocol choices like fast, default, or slow.

Binder Design helps choose between BoltzGen, BindCraft, RFdiffusion, and related tools for protein binder projects. Use it to plan a binder design campaign, compare trade-offs, and pick a workflow for the target type.

Binding Characterization guides SPR and BLI assay planning, troubleshooting, and kinetic data interpretation. Use it when choosing a platform, diagnosing weak or noisy binding, or handling mass transport and regeneration issues.

Bio Agent Skills Hub routes biomedical and bioinformatics requests to the best matching Claude Code skill by searching an index of 1,676 skills, fetching the selected SKILL.md, and following its instructions. Use it for genomics, transcriptomics, single-cell, proteomics, clinical, and multi-omics tasks.

Bio Analysis System designs the analysis layer of a manuscript by mapping figures and tasks to quantitative, qualitative, and biological analyses. Use it to choose methods, tools, and claims for related-work-driven paper planning.

Bio Dataset Search finds suitable biomedical datasets for a research topic and maps them to defined tasks. Use it to extract datasets from papers, search public repositories, and normalize metadata for benchmark planning.

Boltz predicts protein complexes, protein-ligand complexes, and other biomolecular structures with Boltz-1/Boltz-2. Use it for binder validation or open-source structure prediction on local GPU resources.

BoltzGen designs all-atom protein binders and peptides with YAML-configured diffusion. Use it for side-chain aware designs, small-molecule binding, or precise interface geometry; use RFdiffusion for backbone-only work.

Campaign Manager turns binder design goals into runnable pipelines and estimates designs, time, cost, and expected yield. It is used to assess campaign health, diagnose QC failures, and choose among protein design tools.

Cell-Free Expression gives guidance for optimizing cell-free protein synthesis experiments, including template design, yield troubleshooting, and folding difficult proteins. Use it when planning CFPS runs or diagnosing low expression, aggregation, or disulfide issues.

Chai Structure Prediction runs Chai-1 to predict protein-protein, protein-ligand, and protein-nucleic acid complexes. Use it for binder validation, high-throughput structural prediction, or when you want an MSA-free alternative to AlphaFold2.

ESM2 produces protein embeddings and pseudo-log-likelihood scores for sequence plausibility. Use it for clustering, variant effect prediction, and filtering designed sequences before downstream analysis.

Foldseek searches protein 3D structures for similar folds, structural homologs, and remote homologs. Use it to query PDB, AlphaFold, or other structure databases and to cluster structures by similarity.

LigandMPNN designs protein sequences around bound ligands, metals, cofactors, or nucleic acids. Use it for enzyme active sites, binding pocket optimization, and other ligand-aware sequence design tasks.

PDB Access fetches protein structures and metadata from RCSB PDB, and can search similar structures or extract chains and regions. Use it to prepare targets for binder design or inspect interfaces.

Protein Design Workflow gives end-to-end guidance for protein design pipelines, from target preparation and backbone generation to sequence design, validation, and filtering. Use it when planning a new campaign, estimating compute, or coordinating multiple design tools.

Protein QC filters protein design candidates using structural, binding, expression, and sequence-liability thresholds. Use it to screen designs, build multi-stage pipelines, and rank candidates with composite scores.

ProteinMPNN designs amino acid sequences for a given protein backbone using inverse folding. Use it for redesigning structures, fixing selected residues, or generating variants for expression, stability, and multi-state design.

RFDiffusion generates protein backbones for de novo design, binder scaffolds, motif scaffolding, and symmetric oligomers. Use it when you need a backbone to pass to proteinmpnn, alphafold, chai, or protein-qc.

Setup helps users install Modal, authenticate it, and clone biomodals so protein design tools can run. Use it when commands fail, Modal is missing, or someone is starting the environment for the first time.

SolubleMPNN designs protein sequences with a soluble model variant for E. coli expression and higher solubility. Use it to reduce aggregation or inclusion bodies when standard ProteinMPNN is too hydrophobic.

UniProt retrieves protein sequences, annotations, domain boundaries, variants, and cross-references from the UniProt REST API. Use it to look up proteins by accession or gene name and to find related PDB structures.

ipSAE ranks protein binder designs using interprotein Score from Aligned Errors (ipSAE). Use it to filter AF2, AF3, or Boltz predictions and prioritize designs for experimental testing.